🔹 AWS Certified Machine Learning – Associate (MLA-C01) – Amazon Web Services | Sep 7, 2025
🔹 AWS Certified Data Engineer – Associate (DEA-C01) – Amazon Web Services | Oct 12, 2025
🔹 AWS Certified Cloud Practitioner (CLF-C02) – Amazon Web Services | Jul 26, 2025
🔹 Microsoft Power BI Data Analyst Associate (PL-300) – via Coursera, issued by Microsoft
🔹 Passionate about AI, Deep Learning, and Scalable Data Solutions
🔹 Experienced in Python, Machine Learning, Cloud Deployment & Automation
- AWS Bedrock (Claude 3.5 Sonnet, Titan Embeddings)
- AWS Lambda, S3, ECR
- LangChain for LLM orchestration
- Vector Databases: FAISS
- Python
- SQL
- Power BI
- Streamlit
- Docker
- GitHub/Git
- Agile / Project Management
- Supervised Learning: Linear Regression, Logistic Regression, SVM, KNN
- Unsupervised Learning: K-means, Hierarchical Clustering, PCA
- Deep Learning: CNN, RNN, LSTMs, GANs, Transformers
- Libraries & Frameworks: TensorFlow, Keras, PyTorch, Scikit-learn
- Databases: MySQL, MongoDB
- Cloud Computing: AWS (S3, EC2, SageMaker, Lambda)
- Big Data: Hadoop, PySpark
- Power BI
- Tableau
- Plotly
- ML Libraries: XGBoost
, LightGBM, CatBoost
- Data Preprocessing: Pandas, NumPy, Seaborn
- NLP: ALBERT, ANLTK, SpaCy, Transformers, Gensim
✅ Developed predictive models with 90%+ accuracy
✅ Optimized ML models using hyperparameter tuning & feature selection
✅ Built automated ML pipelines with Scikit-learn & TensorFlow
Proficient in: Statistical Analysis, Data Cleaning, Outlier Detection, Hypothesis Testing
🔹 Bug Classification and Prioritization
- Data Labeling: Manually labeled 400+ records to create a high-quality training dataset.
- Multiple ML Approaches: Implemented RNN, LSTM, TF-IDF with ML models, and ALBERT embeddings with Random Forest to find the most effective classification method.
- Custom Classification System: Designed a 5-category bug classification model, improving dataset usability.
- Class Imbalance Handling: Generated additional samples for underrepresented categories to enhance model training.
- Data Cleaning & Refinement: Improved dataset quality by replacing misleading words, enhancing class representation and model accuracy.
- Performance Improvement: Achieved 80% accuracy using ALBERT embeddings with Random Forest, significantly outperforming traditional methods.
🔹 Financial & Forex Market Prediction
- Time Series Analysis: Used LSTM & GRU networks to predict forex trends based on historical data.
- Feature Engineering: Extracted critical macroeconomic indicators, sentiment analysis from news, and technical indicators to enhance model performance.
- Automated Trading Signals: Developed a real-time predictive system that generates buy/sell signals based on ML-driven insights.
- Live Data Integration: Integrated Yahoo Finance API to fetch real-time forex market data for continuous model updating.
- Risk Management: Implemented volatility-adjusted stop-loss strategies to improve trading accuracy and mitigate financial risk.
- Performance Metrics: Achieved +10% higher accuracy than traditional moving average strategies, optimizing trade profitability.
🔹AWS EC2 Instance** - Link to your cloud project
🔹PowerBI Sevices** - [https://app.powerbi.com/groups/me/reports/58e7aaeb-a484-4f3d-96fc-f28cc4282fa6/4624f63d7e341548377b?experience=power-bi]